NetworkAI: An Intelligent Network Architecture for Self-Learning Control Strategies in Software Defined Networks

Haipeng Yao, Tianle Mai, Xiaobin Xu, Peiying Zhang, Maozhen Li, Yunjie Liu

Abstract: The past few years have witnessed a wide deployment of software defined networks facilitating a separation of the control plane from the forwarding plane. However, the work on the control plane largely relies on a manual process in configuring forwarding strategies. To address this issue, this paper presents NetworkAI, an intelligent architecture for self-learning control strategies in software defined networking networks. NetworkAI employs deep reinforcement learning and incorporates network monitoring technologies, such as the in-band network telemetry to dynamically generate control policies and produces a near optimal decision. Simulation results demonstrated the effectiveness of NetworkAI.